Instructions to use matrs01/AI_tutor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use matrs01/AI_tutor with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="matrs01/AI_tutor")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("matrs01/AI_tutor")
model = AutoModelForCausalLM.from_pretrained("matrs01/AI_tutor", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use matrs01/AI_tutor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "matrs01/AI_tutor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "matrs01/AI_tutor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/matrs01/AI_tutor

SGLang

How to use matrs01/AI_tutor with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "matrs01/AI_tutor" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "matrs01/AI_tutor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "matrs01/AI_tutor" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "matrs01/AI_tutor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use matrs01/AI_tutor with Docker Model Runner:
```
docker model run hf.co/matrs01/AI_tutor
```

matrs01 commited on Jun 1, 2024

Commit

c04a54b

verified ·

1 Parent(s): c8ada57

Trained with Unsloth

Browse files

Files changed (5) hide show

config.json +3 -3
model-00001-of-00003.safetensors +2 -2
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +2 -2
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/matrenok/courses/MNLP_course/project/experiment_3_dpo/outputs/checkpoint-550_merged_16bit",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,7 +15,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "sliding_window": null,
@@ -24,5 +24,5 @@
   "transformers_version": "4.41.0",
   "unsloth_version": "2024.5",
   "use_cache": true,
-  "vocab_size": 32000
 }

 {
+  "_name_or_path": "/home/matrenok/courses/MNLP_course/project/experiment_3_sft_data_v2/outputs/checkpoint-550_merged_16bit",
   "architectures": [
     "MistralForCausalLM"
   ],
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 770,
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "transformers_version": "4.41.0",
   "unsloth_version": "2024.5",
   "use_cache": true,
+  "vocab_size": 32768
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf193327a46e6bd4bfb45759a1a35caa502c7607aca4117324ee30bced7dd15
-size 4943162240

 version https://git-lfs.github.com/spec/v1
+oid sha256:9e63a748961055039beb361df1f09d1aac9c9c309d759d0d7fef34a14ea744fe
+size 4949453696

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:879d28b2a328714050c5829040d89701cc518c4ce804176a8d1aea4de9c05a34
 size 4999819232

 version https://git-lfs.github.com/spec/v1
+oid sha256:490856821c0bf97275605c389437ec157ae6c511b5832d50616146d70be6ce79
 size 4999819232

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10dffb24b73c805f5dbd5ff59f162e19805e14b428fa4fb2b0c49523771cbe5
-size 4540516256

 version https://git-lfs.github.com/spec/v1
+oid sha256:440940ddb38d7e2a88e28b1ed169de1e5f426bd641c4968de9764e123c86b669
+size 4546807712

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",

 {
   "metadata": {
+    "total_size": 14496047104
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",